kiranpantha commited on
Commit
8b1f768
·
verified ·
1 Parent(s): 54019a2

Training in progress, step 300

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-large-v3-turbo",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -7,17 +7,14 @@
7
  "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
- "begin_suppress_tokens": [
11
- 220,
12
- 50256
13
- ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
  "d_model": 1280,
17
  "decoder_attention_heads": 20,
18
  "decoder_ffn_dim": 5120,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 4,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
  "encoder_attention_heads": 20,
@@ -33,16 +30,17 @@
33
  "mask_time_length": 10,
34
  "mask_time_min_masks": 2,
35
  "mask_time_prob": 0.05,
 
36
  "max_source_positions": 1500,
37
  "max_target_positions": 448,
38
  "median_filter_width": 7,
39
  "model_type": "whisper",
40
  "num_hidden_layers": 32,
41
  "num_mel_bins": 128,
42
- "pad_token_id": 50257,
43
  "scale_embedding": false,
44
  "torch_dtype": "float32",
45
- "transformers_version": "4.46.3",
46
  "use_cache": true,
47
  "use_weighted_layer_sum": false,
48
  "vocab_size": 51866
 
1
  {
2
+ "_name_or_path": "openai/whisper-large-v3",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
7
  "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": null,
 
 
 
11
  "bos_token_id": 50257,
12
  "classifier_proj_size": 256,
13
  "d_model": 1280,
14
  "decoder_attention_heads": 20,
15
  "decoder_ffn_dim": 5120,
16
  "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 32,
18
  "decoder_start_token_id": 50258,
19
  "dropout": 0.0,
20
  "encoder_attention_heads": 20,
 
30
  "mask_time_length": 10,
31
  "mask_time_min_masks": 2,
32
  "mask_time_prob": 0.05,
33
+ "max_length": null,
34
  "max_source_positions": 1500,
35
  "max_target_positions": 448,
36
  "median_filter_width": 7,
37
  "model_type": "whisper",
38
  "num_hidden_layers": 32,
39
  "num_mel_bins": 128,
40
+ "pad_token_id": 50256,
41
  "scale_embedding": false,
42
  "torch_dtype": "float32",
43
+ "transformers_version": "4.47.1",
44
  "use_cache": true,
45
  "use_weighted_layer_sum": false,
46
  "vocab_size": 51866
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a76c3e6b667ad99bbed1e07e8e20a06413b74b8f95b28684ab0a6e81e6ffb1
3
+ size 4993448880
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d871c1290cdf74ee63ed209f7f07306ee618712fb4b65d2466324c08531e00a6
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan05_18-37-57_idc-training-gpu-compute-27/events.out.tfevents.1736102278.idc-training-gpu-compute-27.4006726.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ad6e2478fe8c36f8799a4751ddd865475e61c7a49ad09d615ef79aa10b4ae9
3
+ size 6295
runs/Jan05_18-42-55_idc-training-gpu-compute-27/events.out.tfevents.1736102576.idc-training-gpu-compute-27.4075677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285a97dc04e838018681b2b882226766843d745766e4acc4939129329535a90b
3
+ size 8756
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea5feccd1d4e97d33f296db6d79f944c55700e9f6d845a90c1637ac814f9742
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da5f545b8a59752bafcf566f86dd5624c433e4bb9e73a211260425851ca7ed0
3
+ size 5496